Diagnosis Of Caries Research Articles

Panoramik Radyograflar İnterproksimal Çürük Tanısında Ne Kadar Kullanışlıdır? Diş Hekimliği Öğrencileri ve Diş Hekimleriyle Yapılan Bir Çalışma

Purpose: It was aimed to investigate the usability of panoramic radiographs without bitewing radiographs in the diagnosis of interproximal caries and to compare the performance of trainee dentists and dentists in the diagnosis of interproximal caries on panoramic radiographs.
 Material and Method: 20 4th grade, 20 5th grade students studying at Erciyes University Faculty of Dentistry and 20 general dentists were included in the study. In the study, images of 11 individuals who had both panoramic and bitewing taken on the same day within the indication in 2020 were used. Initially, radiographs were evaluated by three Oral, Dental and Maxillofacial Radiology research assistants, and caries on the interproximal surfaces of posterior teeth were recorded with a consensus on bitewing radiographs. Second, the participants who agreed to participate in the study evaluated only the panoramic radiographs and coded the lesions at the interfaces of the premolar and molar teeth as “0”, “1”, “2”, and “3” according to their depth. Statistical analyzes were performed with SPSS v.22 software. Results: Dentists were the most successful in terms of correct evaluation of teeth in terms of the presence or absence of caries (80.52%). This was followed by class 5 (67.29%) and class 4 (60.12%) students. (p

Artificial intelligence in the diagnosis of dental diseases on panoramic radiographs: a preliminary study

BackgroundArtificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple dental diseases on PRs, and to initially evaluate its performance.MethodsThe AI framework was developed based on 2 deep convolutional neural networks (CNNs), BDU-Net and nnU-Net. 1996 PRs were used for training. Diagnostic evaluation was performed on a separate evaluation dataset including 282 PRs. Sensitivity, specificity, Youden’s index, the area under the curve (AUC), and diagnostic time were calculated. Dentists with 3 different levels of seniority (H: high, M: medium, L: low) diagnosed the same evaluation dataset independently. Mann-Whitney U test and Delong test were conducted for statistical analysis (ɑ=0.05).ResultsSensitivity, specificity, and Youden’s index of the framework for diagnosing 5 diseases were 0.964, 0.996, 0.960 (impacted teeth), 0.953, 0.998, 0.951 (full crowns), 0.871, 0.999, 0.870 (residual roots), 0.885, 0.994, 0.879 (missing teeth), and 0.554, 0.990, 0.544 (caries), respectively. AUC of the framework for the diseases were 0.980 (95%CI: 0.976–0.983, impacted teeth), 0.975 (95%CI: 0.972–0.978, full crowns), and 0.935 (95%CI: 0.929–0.940, residual roots), 0.939 (95%CI: 0.934–0.944, missing teeth), and 0.772 (95%CI: 0.764–0.781, caries), respectively. AUC of the AI framework was comparable to that of all dentists in diagnosing residual roots (p > 0.05), and its AUC values were similar to (p > 0.05) or better than (p < 0.05) that of M-level dentists for diagnosing 5 diseases. But AUC of the framework was statistically lower than some of H-level dentists for diagnosing impacted teeth, missing teeth, and caries (p < 0.05). The mean diagnostic time of the framework was significantly shorter than that of all dentists (p < 0.001).ConclusionsThe AI framework based on BDU-Net and nnU-Net demonstrated high specificity on diagnosing impacted teeth, full crowns, missing teeth, residual roots, and caries with high efficiency. The clinical feasibility of AI framework was preliminary verified since its performance was similar to or even better than the dentists with 3–10 years of experience. However, the AI framework for caries diagnosis should be improved.

Dental caries and non caries detection using deep learning

Cavities are the most common indication of dental caries, a contagious condition that leads to the deterioration of the tooth's structure. Dental caries has been identified as one of the most common oral health issue. This research has been conducted to identify them early, owing to the discomfort and high expense of treatment. Artificial intelligence has been utilized in recent years to create models which can forecast the risk of dental caries due to restrictions in medical research in oral healthcare, such as the high costs and lengthy requirements. Data for our study were collected from Khyber College of Dentistry and Hospital. On this data, a number of Deep Learning algorithms were implemented, and their performances were evaluated using recall, precision, F1-score, and accuracy. In comparison to CNN, LeNet and AlexNet deep learning techniques, VGG16 has the best performance, scoring accuracy of 98.99%, F1-score of 0.96% with precision of 0.95%, and a recall of 0.97%. This suggested paper demonstrated that DL is strongly advised for dental professionals to use in helping them make decisions for the early diagnosis and treatment of dental caries.

Recent innovations and technological advancements in Dentistry and Medicine

The newer innovations play an important role in the earlier diagnosis of dental caries based on near-infrared transillumination imaging such as Diagnocam and Soprocare intraoral digital cameras, which aid in the diagnosis of dental caries and also differentiate old and newer dental plaques, respectively. Nanoparticles used as carriers for effective and targeted drug therapies in the treatment of rheumatoid arthritis of the temporomandibular joint (TMJ) and candidiasis among chronic denture wearers provided better-increased bioavailability than oral formulations. Artificial intelligence (AI) uses machines to simulate intelligent human behavior. Augmented reality has been presented as a cognitive extension of AI in health care, emphasizing the auxiliary and supplemental roles of dental and medical practitioners. The article enlightens readers with newer diagnostic methods in dentistry and medicine and innovations such as Surface Topography-Assisted Robotic Superstructures (STARS), Prostate-Specific Membrane Antigen Ligand Positron Emission Tomography/Computed Tomography (PSMA-PETCT), toothbrushes with augmented reality, new hydrogel-based electrodes for Brain-Computer Interface (BCI) applications, and robotics in dentistry.

Türkiye’deki Çocuk Diş Hekimlerinin Dental Radyografi Bilgi ve Tutumlarının Değerlendirilmesi

Aim: The aim of this study is to evaluate the knowledge levels and attitudes of pediatric dentists regarding the use of dental radiography through an online survey. Materials and Method: A data collection form consisting of a total of 17 questions and 2 basic parts, which was prepared in accordance with the current guidelines of the European Academy of Pediatric Dentistry regarding the use of radiography in 2020, was used. The first part of the form was prepared to evaluate the sociodemographic characteristics of the participants and the second part of the form was for the evaluation of the participants’ level of knowledge about the use of radiography in pediatric dentistry. In the analysis of the data, descriptive statistics, mean values, frequencies and proportions were calculated. The chisquare test was used to determine the association between categorical variables. Results: 131 pediatric dentists participated in the study. In accordance with the Guideline recommendation, 40.5% of dentists stated that they preferred bite-wing radiographs as the first choice for the detection and diagnosis of dental caries and 77% stated that they preferred periapical radiographs as the first choice for dental trauma. Conclusion: Even though pediatric dentists in Türkiye usually choose the most appropriate radiographic technique for most clinical situations; knowledge levels need to be increased for more precise diagnosis and treatment planning and radiation protection.

Application of artificial intelligence and telemedicine in dentistry: prospects and review

The use of artificial intelligence (AI) in dentistry is a promising field that has the potential to revolutionize the healthcare sector and improve the quality of dental care. Researchers are also discussing methods of telemedicine health screening, including the use of questionnaires and AI to analyze the data obtained. AI can be used to automatically analyze X-rays and detect dental and gum disease, such as cavities, periodontitis and others. AI can help determine the best therapy and medication dosage for each patient based on his or her individual characteristics. Moreover, AI can be used to plan surgical procedures, such as dental implants. Also, current techniques include the use of telemedicine for online consultations, diagnosis, and treatment of dental and gum disease. For the purposes of this review, we will limit ourselves to a brief list of digital advances in caries diagnosis and prognosis.

Interactive computer-assisted learning as an educational method for learning pediatric interproximal dental caries identification

We developed a web-based tool to measure the amount and rate of skill acquisition in pediatric interproximal caries diagnosis among pre- and postdoctoral dental students and identified variables predictive for greater image interpretation difficulty. In this multicenter prospective cohort study, a convenience sample of pre- and postdoctoral dental students participated in computer-assisted learning in the interpretation of bitewing radiographs of 193 children. Participants were asked to identify the presence or absence of interproximal caries and, where applicable, locate the lesions. After every case, participants received specific visual and text feedback on their diagnostic performance. They were requested to complete the 193-case set but could complete enough cases to achieve a competency performance standard of 75% accuracy, sensitivity, and specificity. Of 130 participants, 62 (47.7%) completed all cases. The mean change from initial to maximal diagnostic accuracy was +15.3% (95% CI, 13.0-17.7), sensitivity was +10.8% (95% CI, 9.0-12.7), and specificity was +15.5% (95% CI, 12.9-18.1). The median number of cases completed to achieve competency was 173 (interquartile range, 82-363). Of these 62 participants, 45 (72.6%) showed overall improvement in diagnostic accuracy. Greater numbers of interproximal lesions (P < .001) and the presence of noninterproximal caries (P < .001) predicted greater interpretation difficulty. Computer-assisted learning led to improved diagnosis of interproximal caries on bitewing radiographs among pre- and postdoctoral dental students.

Fifty years of progress in paediatric dentistry

Progress in paediatric dentistry over the last half a century has been evident across all areas of the speciality. This article highlights significant changes in the diagnosis, prevention and management of dental caries, traumatic dental injuries, developmental enamel defects, tooth erosion, dental fear and anxiety and safeguarding children. The dedication of clinicians and researchers along with advances in material science and technology have supported this progress. We discuss the importance of working with those both within and outside of the specialty in order to collaborate to improve children’s oral health. There have been significant strides in the provision of child-centred holistic care and research. Reviewing the advancements made over this period has set a high precedent for making further progress within paediatric dentistry over the next 50 years. CPD/Clinical Relevance: Knowledge of key advances in the field of paediatric dentistry will facilitate good diagnosis and treatment of younger patients.

Black to Dental Update and beyond!

Dental caries is one of the most common non-communicable diseases globally, and while entirely preventable, it still accounts for a huge economic burden in the form of operative management, which ranges from minimally invasive techniques to extensive direct and indirect restorations, root canal treatment and ultimately extraction. In this article, we look at the marked changes in caries epidemiology, detection, diagnosis, assessment and management that has taken place in the past five decades since Dental Update was first published, and reflect on how this has had an impact on the oral health of our patients today. CPD/Clinical Relevance: Awareness of changes in caries understanding over the last five decades is of value to clinicians.

Comparative evaluation of predictors of dental caries among adult population in a metropolitan city in North West Nigeria: A case-control study

Background: Dental caries as a disease entity has not been eradicated but controlled worldwide. The predictors of dental caries play a significant role in the holistic approach in the management of dental caries. The aim of this study is to evaluate the predictors of dental caries among adult population in North West Nigeria.&#x0D; Material and Methods: The study populations consist of adults between 20-60 years old, with diagnosis of dental caries (case) and those without dental caries (control), both were confirmed after intraoral examination. A multistage sampling technique was employed to select the study respondents. Mouth mirror and caries explorer (dental probe) were used for intraoral examination to confirm diagnosis of dental caries. An initial calibration of the research assistants was done on intraoral examination by the principal researcher, assessing the same respondents examined by the research assistants. Data was analyzed using SPSS Statistical software version 20.0.&#x0D; Results: The older age groups were 4% less likely to have caries (p &lt;0.001, AOR= 0.96, 95% CI =0.94-0.98) while participants that took local sweet drinks were 2.8 times more predisposed. Respondents without scaling and polishing were 4.8 times more likely to have caries (p=0.01, AOR= 4.82 95% CI=1.45-16.05) while those who received oral hygiene instructions were 72% less likely to have caries (p&lt;0.001, AOR=0.28 95% CI= 0.11-0.67).&#x0D; Conclusion: Age, family history, teeth cleaning method, use of fluoride toothpaste and source of oral health maintenance were found to be independent predictors of dental caries.

Evaluation of the salivary pH and its correlation with dental caries in a population of Brazilian adolescents

Dental caries is one of the most prevalent diseases around the world and saliva plays an essential role in controlling the evolution of the disease. This study aimed to investigate if salivary pH is correlated with dental caries in a population of Brazilian adolescents. Adolescents, of both sexes, were submitted to clinical examinations for diagnosis of dental caries according to Decay, Missing, and Filling Teeth index (DMFT). The adolescents were allocated into two groups: i. unaffected by caries (DMFT= 0) and ii. affected by caries (DMFT≥ 1). Saliva samples were collected, and the pH was measured using a pH meter. 672 adolescents were examined, mean age of 12 years old (± 0.45), 305 (45.4%) male and 367 (54.6%) female. The DMFT index in the overall population was 1.46; 49% of the population had DMFT=0. The main result point to a negative correlation but significant between dental caries and salivary pH for the total sample (r= -0.119; CI= -0.195 to -0.042; p=0.002) and for males (r= -0.143; CI= -0.254 to -0.028; p=0.012), and a borderline value for females (r= -0.099; CI= -0.202 to 0.006; 0.057). This study showed that there is a correlation between salivary pH and dental caries in examined adolescents.

A Preliminary Study of A Lactic Acid Biosensor for the Early Detection of Dental Caries

Statement of Problem: Many mechanisms in the formation of dental caries, but the common point of these mechanisms is the proliferation of microorganisms in the mouth and mostly on the tooth surface. Objective: Although there are approximately 200 to 300 different microorganisms in human dental plaque, Neisseria spp. and S. mutans. The common point of these microorganisms is that they produce lactic acid. In this study, it is aimed to use a biosensor, which is a bioelectrochemical measurement system that combines the measurementcapability of physical analysis systems and the specificity of biochemical systems.Material-Method: In this study, lactate oxidase enzyme was immobilised on the gold working electrode surface by means of bovine serum albumin and gelatine. The enzyme was arrested on the electrode surface with the aid of the cross-linking agent glutaraldehyde. Cyclic voltammetry current scanning was performed in lactic acid biosensor preliminary studies. Optimisation studies were conducted in the current range obtained fromthe peak in the cyclic voltammogram. Within the scope of the optimisation studies, optimum operating temperature and optimum operating pH of the biosensor were tested.Results: An anodic peak at +0.2 V potential was obtained in the cyclic voltammogram drawn according to the reaction on the working electrode surface. In the optimisation studies conducted, it was found that the optimum operating conditions of the biosensor were at 35 °C and pH 6.5.Conclusion: According to the data obtained from the pre-study of the bioelectrochemical method, the concentration of lactic acid in the solution can be determined. With the completion of further studies, a portable lactic acid biosensor can be made. As a result, as a result of the preliminary study, the lactic acidbiosensors designed to determine in vitro lactic acid for the early diagnosis of dental caries in the future is promising.

CariesFG: A fine-grained RGB image classification framework with attention mechanism for dental caries

Dental caries is one of the most prevalent oral diseases, and deep learning methods have been used for caries diagnosis in large populations by leveraging RGB images. The existing attention-based fine-grained image classification methods have the problem of underutilization of features and easy interference by background and irrelevant information. To tackle these issues, we propose a fine-grained RGB image classification framework with attention mechanism for dental caries (CariesFG). Specifically, it consists of 4 components: (1) Multi-Spectral channel Attention Module (MSAM), which can retain the useful frequency components in the feature map. (2) Position Attention Module (PAM), which captures feature dependencies in the spatial dimension. (3) Discriminative Point Selection strategy (DPS), which can find the most discriminative feature points. (4) Graph Convolution and Aggregation module (GCA), which aims to aggregate discriminative feature points at different scales of feature maps. To enhance the ability to extract the discriminative features, PAM and MSAM are integrated into the backbone network to consist of feature extraction networks incorporating attention mechanism. Discriminative feature points at different scales of feature maps are extracted by DPS and aggregated as global discriminative features by GCA. By testing on a caries fine-grained classification dataset, CariesFG achieved an accuracy of 68.36%, an f1-score of 66.77% and a specificity of 84.17%, respectively, significantly outperforming state-of-the-art methods. Moreover, visualization results on attention parts show that CariesFG can effectively learn discriminative features and discriminative parts.

Degree of Concordance Between Cone Beam Computerized Tomography (Cbct) And 2d Digital Radiography System Used for Caries Diagnosis: An Observational Study

Background: Caries is a disease with a high prevalence, which may be due to the lack of adequate methods for its early diagnosis, becomes difficult to detect initial caries lesions in posterior teeth due to the occlusal anatomy of these and because on many occasions they start in the interproximal zone below the contact areas. Different techniques have been used for the diagnosis of caries, such as visual-tactile inspection, radiography, tomography, and transillumination, but none of them seems to have complete sensitivity or specificity. Aim: This study aims to establish the degree of agreement between radiographic diagnosis with 2D intraoral digital radiography in relation to cone beam computed tomography in extracted carious and healthy posterior teeth, practicing the CariesCare International ™ practical guide as a reference. Materials and Methods: A total number of 117 teeth with or without carious lesions were selected. Digital images of all teeth were obtained from 2D digital radiographs (instrumentarium ™ films) obtained with Kavo focus equipment and CBCT scanner I-CAT ™ model 1719, ISI (imaging science international), Pennsylvania (blue sky plan 4 software). Observers evaluated the images for the detection of carious lesions. The sensitivity and specificity ratio between the systems was determined using the area under the curve statistical tool ROC (Receiver Operating Characteristic). For the statistical analysis, the statistical program STATA IC/16 was used, in which the calculation of absolute and relative frequencies for each category of CariesCare international in CBCT and radiography was performed, in addition to the Friedman and post-hoc Wilcoxon test by pairs; the distribution according to the classification of CariesCare international was contrasted between the CBCT slices. The calculation of weighted Kappa and dichotomous Kappa and the calculation of validity (sensitivity and specificity) and prediction (predictive values and predictive ratios) were performed. The distribution according to CariesCare international classification was contrasted between the CBCT slices. Results: The results of the present study confirm that diagnosis of caries with the 2D digital radiographic method, initial caries lesions tend to go undetected relative to CBCT. Conclusion: 2D digital radiographs showed low sensitivity for caries detection and high specificity relative to CBCT for caries lesions in vitro. Diagnosis with 2D digital Rx is considered non-discriminative in identifying initial caries lesions.

The diagnostic performance of the Java-based software colorization tool in the diagnosis of dental caries: an in vitro study.

This in vitro study aimed to compare the diagnostic outcomes of caries detection in premolar and molar teeth on digital periapical radiographs viewed as grayscale images and in the Java-based software (JBS) pseudocolor spectrum. The study comprised 92 premolar or molar human teeth (n = 46 with caries and n = 46 without clinical caries). For each tooth, digital periapical radiographic images (DPRIs), JBS pseudocolor images, and stereomicroscope images were collected, and caries presence and depth were recorded. In JBS pseudocolor images, regions of interest (ROIs) were detected, and ROI values for caries area (ROI1), non-caries area (ROI2), mesial area (ROI3), and distal area (ROI4) were obtained. The degree of inter-observer agreement was determined using the kappa coefficient, and the sensitivity and specificity of the methods were assessed using ROC analysis. While neither method was consistent with stereomicroscopy in determining caries depth (P < .005), for both observers the kappa value of JBS pseudocolor images were slightly higher than those for DPRIs. ROI1 was found to be significantly lower than ROI2 (P < .001), whereas no difference was found between ROI3 and ROI4 (P = .877). For both observers, the sensitivity and specificity obtained from JBS pseudocolor were above 89%. JBS pseudocolor images can be used for caries detection and offer high sensitivity and specificity.

Construction of a caries diagnosis model based on microbiome novelty score.

This study aimed to analyze the bacteria in dental caries and establish an optimized dental-ca-ries diagnosis model based on 16S ribosomal RNA (rRNA) data of oral flora. We searched the public databa-ses of microbiomes including NCBI, MG-RAST, EMBL-EBI, and QIITA and collected data involved in the relevant research on human oral microbiomes worldwide. The samples in the caries dataset (1 703) were compared with healthy ones (20 540) by using the microbial search engine (MSE) to obtain the microbiome novelty score (MNS) and construct a caries diagnosis model based on this index. Nonparametric multivariate ANOVA was used to analyze and compare the impact of different host factors on the oral flora MNS, and the model was optimized by controlling related factors. Finally, the effect of the model was evaluated by receiver operating characteristic (ROC) curve analysis. 1) The oral microbiota distribution obviously differed among people with various oral-health statuses, and the species richness and species diversity index decreased. 2) ROC curve was used to evaluate the caries data set, and the area under ROC curve was AUC=0.67. 3) Among the five hosts' factors including caries status, country, age, decayed missing filled tooth (DMFT) indices, and sampling site displayed the strongest effect on MNS of samples (P=0.001). 4) The AUC of the model was 0.87, 0.74, 0.74, and 0.75 in high caries, medium caries, low caries samples in Chinese children, and mixed dental plaque samples after controlling host factors, respectively. The model based on the analysis of 16S rRNA data of oral flora had good diagnostic efficiency.

Discrimination of tooth composition through temporally shaped femtosecond laser-induced breakdown spectroscopy

Dental caries has attracted widespread concern because of its universality. However, the current diagnosis of dental caries depends largely on naked eyes and dentists' experience, which causes considerable randomness and inaccuracy in the diagnosis. In this study, temporally shaped double pulse (DP) femtosecond laser-induced breakdown spectroscopy (LIBS) has been used for tooth composition detection for the first time. Under the laser fluence of 20 J/cm2, the spectra intensity for DP LIBS with a pulse delay of 200 ps was 13 times higher than that of single pulse. For further prediction, the detection model based on DP LIBS and partial least squares discrimination analysis could discriminate dentin, enamel, and caries with a prediction accuracy of above 90%. This method may provide rapid and accurate feedback to dentists for real-time diagnosis in the future.

A Systematic Review on Artificial Intelligence Applications in Restorative Dentistry

Statement of problem: Artificial intelligence (AI) applications are increasingly used in restorative process. But existing dentistry restoration effectiveness as well as growth and IA applications have not yet been systematically analyzed or documented. Purpose: The goal of such comprehensive evaluation is to discover &amp; assess the abilities associated with artificial intelligence models in restorative dentistry for the analysis of caries as well as vertical tooth fracture, evaluate margins in preparing tooth, and analyze reconstructive failures. Methods: A systematic electronic review of 5 databases was carried out: PubMed/ MEDLINE, World of Science, EMBASE, Scopus and Cochrane. The investigation was carried out manually as well. Research using AI models was chosen on the basis of 4 criterion: dental caries diagnostics, diagnostics, vertical tooth fracture, tooth preparation recognition, &amp; cause of failure of restoration. Both researchers rated the quality of the study for Critical Appraisal Checklist for Quasi-Experimental Studies (nonrandomized experimental studies). The 3rd author was asked for resolving the dispute. Results: 34 researches were made the part of this analysis: from which 29 contains artificial intelligence techniques including the diagnostics or treatment related to caries and its causes according to sensitivity models, 2 to diagnose vertical tooth fractures, 1 to prepare the teeth. Among the studied analysis, the accuracy of caries diagnosis in the AI models was tested from 76-88.3%, sensitivity from 73-90%, as well as specificity from 61.5-93%. In the study, the accuracy of predicted caries ranges from 83.6-97.1%. The performed research showed the accuracy of the analysis of a vertical tooth fracture from 88.3-95.7%. The study, which uses AI models to find a destination, had details with the range of 90.6-97.4%. Conclusions: AI models are a powerful tool for diagnosing caries as well as vertical tooth fractures, recognizing preparation margins and predicting restoration failures. But, the dental use of AI models continues to evolve. More research is needed to evaluate the clinical effectiveness of artificial intelligence models in restorative dentistry. Keyword: Artificial intelligence, restorative dentistry, vertical tooth fractures.

Comparison of early caries diagnosis methods

Relevance. The question of diagnosing tooth decay and, thus, determining treatment methods is still very topical. There is a large number of techniques available for the diagnosis of dental caries in modern dentistry.Objective. The study aimed to compare different caries diagnosis methods to determine the most effective carious lesion detection.Material and methods. We examined in total 45 subjects, 1248 permanent teeth and 5700 tooth surfaces. The dental examination included three diagnostic techniques for each patient: visual-tactile, ICDAS II and quantitative light-induced fluorescence (QLF). The data were processed and presented graphically using Statistica 12.0 (Stat-Soft) and Microsoft Office Excel 2017 software.Results. According to the DMFS index, in the visual-tactile group, the "D" (decayed) was 3.00 ± 0.02 and the "F" (filled) was 1.93 ± 0.02. Caries intensity in this study group was 6.27 ± 0.58. The ICDAS II examination detected the average caries intensity of 6.93 ± 0.56 (p1-2 &lt; 0.001). There were 3.47 ± 0.02 (p1-2 &lt; 0.001) carious lesions. The "F" score was 2.13 ± 0.01 (p1-2 = 0.024). The QLF diagnostic method showed 7.44 ± 0.54 (p1-3 &lt; 0.001, p2-3 = 0.006) as the mean intensity of caries in permanent teeth; there were 3.84 ± 0.02 (p1-3 &lt; 0.001, p2-3 = 0.015) carious lesions and the "F" was 2.27 ± 0.01 (p1-3 = 0.018, p2-3 = 0.520). The "M" score was 0.27 ± 0.01 (p1-2 = 0.999, p1-3 = 0.999, p2-3 = 0.999), according to all applied techniques.Conclusion. The QLF method had the highest sensitivity and was superior to the visual-tactile method and ICDAS II.

Machine learning-based automatic identification and diagnosis of dental caries and calculus using hyperspectral fluorescence imaging.

Precise diagnosis and identification of early dental caries facilitates timely intervention and reverses the progression of the disease. Developing an objective, accurate and rapid caries and calculus automatic identification method advances clinical application and facilitates the promotion and screening of oral health in the community and family. In this study, based on 122 dental surfaces labeled by professional dentists, hyperspectral fluorescence imaging combined with machine learning algorithms was employed to construct a model for simultaneously diagnosing dental caries and calculus. Model trained by fusion features based on spectra, textures, and colors with the integrated learning algorithm has better performance and stronger generalization capabilities. The experimental results showed that the diagnostic model's accuracy, sensitivity, and specificity for identifying four different caries stages and calculus were 98.6%, 98.4%, and 99.6%, respectively. The proposed method can evaluate the whole tooth surface at the pixel level and provides discrimination enhancement and a quantitative parameter, which is expected to be a new approach for early caries diagnosis.